Update README.md

README.md

@@ -22,10 +22,27 @@ This repo contains GGUF format model files for [malhajar's Mistral 7B Instruct v
 - **Language(s) (NLP):** Turkish
 - **Finetuned from model:** [`mistralai/Mistral-7B-Instruct-v0.2`](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
 
+# Quantization methods
+| quantization method | bits | size     | use case                                            | recommended |
+|---------------------|------|----------|-----------------------------------------------------|-------------|
+| Q2_K                | 2    | 2.72 GB  | smallest, significant quality loss  | ❌         |
+| Q3_K_S              | 3    | 3.16 GB  | very small, high quality loss                       | ❌         |
+| Q3_K_M              | 3    | 3.52 GB  | very small, high quality loss                       | ❌         |
+| Q3_K_L              | 3    | 3.82 GB  | small, substantial quality loss                     | ❌         |
+| Q4_0                | 4    | 4.11 GB  | legacy; small, very high quality loss  | ❌         |
+| Q4_K_S              | 4    | 4.14 GB  | small, greater quality loss                         | ❌         |
+| Q4_K_M              | 4    | 4.37 GB  | medium, balanced quality               | ✅         |
+| Q5_0                | 5    | 5.00 GB  | legacy; medium, balanced quality  | ❌         |
+| Q5_K_S              | 5    | 5.00 GB  | large, low quality loss                | ✅         |
+| Q5_K_M              | 5    | 5.13 GB  | large, very low quality loss           | ✅         |
+| Q6_K                | 6    | 5.94 GB  | very large, extremely low quality loss              | ❌         |
+| Q8_0                | 8    | 7.70 GB  | very large, extremely low quality loss   | ❌         |
+| FP16                | 16   | 14.5 GB  | enormous, minuscule quality loss  | ❌  |
+
 ## Prompt Template
 ```
 ### Instruction:
 <prompt> (without the <>)
 ### Response:
 ```
-<!-- description end -->
+<!-- description end -->